A frozen vision transformer plus trainable attention-steering blocks and EWC achieves competitive continual learning accuracy without rehearsal memory.
Coatnet: Marrying convolution and attention for all data sizes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
FCL-ViT: Task-Aware Attention Tuning for Continual Learning
A frozen vision transformer plus trainable attention-steering blocks and EWC achieves competitive continual learning accuracy without rehearsal memory.